Documentation Navigation
Models & pricing / Models / maple-preview
maple-preview Overview
This model's data has not been fully verified and benchmarks may be missing.
maple-preview is a chat-reasoning AI model created by deepgrove, featuring 20.2B parameters and a context window of unknown.
maple-preview is a 20.2B-parameter Mixture-of-Experts (MoE) text generation model developed by deepgrove. Built on the MapleForCausalLM architecture using transformers. Supports en language(s). Released on 2026-08-04 with 190 likes and 419 downloads on Hugging Face.
Model Lineage & Specification
maple-preview is deepgrove's primary release in the current family.
maple-previewComparable models
| Feature | maple-preview | Solar Pro 4 | Qwen3.8 Max Preview | Nemotron 3 Ultra |
|---|---|---|---|---|
| Description | maple-preview is a 20.2B-parameter Mixture-of-Experts (MoE) text generation mode... | Solar Pro 4 is a large language model from Upstage built for enterprise workflow... | Preview Qwen flagship for million-token multimodal reasoning and long-horizon ag... | NVIDIA Nemotron 3 Ultra is a flagship open-weight frontier LLM family engineered... |
| API Identifier | maple-preview | upstage-solar-pro-4 | alibaba-qwen3.8-max-preview | nvidia-nemotron-3-ultra |
| Parameters | 20.2B | — | — | 550B total / 55B active |
| Context Window | unknown | 524288 | 1M tokens | 1M tokens |
| License / Type | open weights | api only | api only | open weights |
maple-preview
maple-preview is a 20.2B-parameter Mixture-of-Experts (MoE) text generation mode...
maple-previewSolar Pro 4
Solar Pro 4 is a large language model from Upstage built for enterprise workflow...
upstage-solar-pro-4Qwen3.8 Max Preview
Preview Qwen flagship for million-token multimodal reasoning and long-horizon ag...
alibaba-qwen3.8-max-previewNemotron 3 Ultra
NVIDIA Nemotron 3 Ultra is a flagship open-weight frontier LLM family engineered...
nvidia-nemotron-3-ultramaple-preview is a 20.2B-parameter Mixture-of-Experts (MoE) text generation model developed by deepgrove. Built on the MapleForCausalLM architecture using transformers. Supports en language(s). Released on 2026-08-04 with 190 likes and 419 downloads on Hugging Face.